CN119272140B - Method, device, equipment and medium for detecting data abnormality in cell gluing process - Google Patents
Method, device, equipment and medium for detecting data abnormality in cell gluing process Download PDFInfo
- Publication number
- CN119272140B CN119272140B CN202411799606.6A CN202411799606A CN119272140B CN 119272140 B CN119272140 B CN 119272140B CN 202411799606 A CN202411799606 A CN 202411799606A CN 119272140 B CN119272140 B CN 119272140B
- Authority
- CN
- China
- Prior art keywords
- value
- sampling
- data
- proportion
- preset index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The application discloses a data anomaly detection method, device, equipment and medium in a cell gluing process. The method comprises the steps of sampling proportion data of various glues in mixed glue adopted in a cell gluing process to obtain sampling data, obtaining preset indexes corresponding to each sampling data in the first numerical value sampling data when the number of the sampling data reaches a first numerical value, wherein the preset indexes are used for representing the trend of the sampling data changing along with time, obtaining two unequal preset index values in a preset sliding window according to the first numerical value preset indexes, and judging whether the proportion of the mixed glue is abnormal according to the two unequal preset index values. The method provided by the embodiment of the application can detect the proportion data of various glues in the mixed glue, so that abnormal proportion of the glues can be found in time in the cell gluing process, and the situation of poor bonding strength of the mixed glue caused by abnormal proportion of the glues is reduced.
Description
Technical Field
The application relates to the technical field of battery manufacturing, in particular to a data abnormality detection method, device, equipment and medium in a cell gluing process.
Background
With the development of new energy technology, batteries, particularly power batteries, have been increasingly used in various technical fields such as electric vehicles. The manufacturing process of the battery comprises the process steps of gluing the battery core, and the gluing of the surface of the battery core can play roles in fixing, insulating and radiating the battery core.
Different cell materials or structures are suitable for glues with different characteristics, the curing time and the curing required conditions of a single glue are generally not suitable for various application scenes, and the adaptability is poor, so that the mixed glue formed by mixing various glues is adopted in the cell gluing process in the related technology. The proportion of various kinds of mixed glue can enable the mixed glue to reach better bonding strength within a certain range, and the bonding strength can be influenced by abnormal proportion of the mixed glue. However, the related art lacks monitoring to the glue proportion of the mixed glue in the cell glue coating process, and the abnormal situation of the glue proportion cannot be found in time in the cell glue coating process, so that the adhesive strength of the mixed glue is poor.
The statements made above merely serve to provide background information related to the present disclosure and may not necessarily constitute prior art.
Disclosure of Invention
In view of the problem that the abnormal glue proportion of the mixed glue in the cell gluing process cannot be found in time due to lack of monitoring of the glue proportion of the mixed glue in the cell gluing process, so that the adhesive strength of the mixed glue is poor, the application provides a data abnormality detection method, device, equipment and medium in the cell gluing process, so as to detect the proportion data of various glues in the mixed glue, and the abnormal glue proportion is found in time in the cell gluing process, so that the situation that the adhesive strength of the mixed glue is poor due to abnormal glue proportion is reduced.
In a first aspect of the embodiment of the present application, a method for detecting data anomalies in a process of coating a battery cell is provided, including:
sampling proportion data of various glues in mixed glues adopted in the cell gluing process to obtain sampling data;
acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time;
Acquiring two unequal preset index values in a preset sliding window aiming at the first numerical value preset indexes;
and judging whether the proportion of the mixed glue is abnormal or not according to the two unequal preset index values.
According to the data anomaly detection method in the cell gluing process provided by the embodiment of the application, the proportion data of various glues in the mixed glue can be detected, so that the abnormal proportion condition of the glues can be found in time in the cell gluing process, and the condition of poor bonding strength of the mixed glue caused by the abnormal proportion of the glues is reduced.
In some embodiments of the present application, the preset index includes an exponentially weighted moving average EWMA, and the determining whether the proportion of the mixed glue is abnormal according to the two unequal preset index values includes:
Judging whether the proportion of the mixed glue is abnormal or not according to the sampling data with the current sampling sequence number of a second numerical value and the two unequal preset index values, wherein the sampling sequence number is a sequence number for sequencing all the current sampling data according to sampling time, and the second numerical value is the sum of the first numerical value and 1.
The exponential weighted moving average EWMA is used as a preset index, so that the trend of the sampled data along with the time change can be revealed, and the noise can be reduced.
In some embodiments of the present application, the determining whether the proportion of the mixed glue is abnormal according to the current sampling data with the second sampling number and the two unequal preset index values includes:
Judging that the proportion of the mixed glue is normal when the current sampling data with the second numerical value belongs to a first closed interval, wherein the left end point of the first closed interval is smaller than the smaller value of the two unequal preset index values, and the right end point of the first closed interval is larger than the larger value of the two unequal preset index values;
And under the condition that the current sampling data with the sampling serial number of the second numerical value does not belong to the first closed interval, judging that the proportion of the mixed glue is abnormal.
Whether the proportion of the mixed glue is abnormal or not is judged by whether the current sampling data with the sampling sequence number of the second numerical value belongs to the first closed interval or not, and the accuracy rate of the judgment result is higher.
In some embodiments of the present application, the left end point of the first closed interval is the product of the EWMA of the smaller value and a third value, the right end point of the first closed interval is the product of the EWMA of the larger value and a fourth value, the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2. The first closed interval is set based on two unequal preset index values in the preset sliding window, so that accuracy of a judgment result is improved, and false alarm and missing report of abnormal conditions caused by data fluctuation are reduced.
In some embodiments of the present application, the sampling the ratio data of various glues in the mixed glue used in the cell glue coating procedure to obtain sampling data includes:
sampling the proportion data of various glues in the mixed glue to obtain an original sampling value;
Detecting whether an original sampling value is an abnormal value or not;
Removing the original sampling value under the condition that the original sampling value is an abnormal value, filling the removed original sampling value, and taking the filled value as sampling data;
and taking the original sampling value as the sampling data in the case that the original sampling value is not an abnormal value.
Therefore, abnormal values can be removed, interference caused by the abnormal values is reduced, and the accuracy of abnormal judgment results of various glue proportions in the mixed glue is further improved.
In some embodiments of the present application, the sampling the ratio data of various glues in the mixed glue used in the cell glue coating procedure to obtain sampling data further includes:
And storing the sampled data into a pre-established data queue according to the sampling time sequence, wherein the capacity of the data queue is the first numerical value data. Thus, the management and the calling of the sampling data are facilitated, and the working efficiency is improved.
In some embodiments of the application, the method further comprises:
And under the condition that the proportion of the mixed glue is normal, replacing the sampling data with the earliest sampling time in all the current sampling data by using the sampling data with the second numerical value, deleting the first EWMA, and returning to the preset index corresponding to each sampling data in the acquired first numerical value sampling data, wherein the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time. Therefore, the on-line detection of the abnormal proportion data of the mixed glue in the cell gluing process can be realized, the influence of the discrete degree of the sampled data is considered, the abnormal fluctuation condition of the data is easy to capture, and the abnormal proportion condition can be accurately and timely found. In addition, the updating of two unequal preset index values in the preset sliding window can be realized, so that the dynamic adjustment of a comparison section for judging whether the proportion of the mixed glue is abnormal is realized, compared with the situation that the generalization capability of an abnormality detection method is reduced due to the fact that the comparison section is manually set in the related art, the generalization capability of the detection method of the embodiment is stronger, and the over-killing condition can be reduced by dynamically adjusting the comparison section.
In some embodiments of the present application, the two unequal preset index values are respectively a preset index value of the nth percentile and a preset index value of the mth percentile, wherein N and M are preset values, N is equal to or less than 100, M is equal to or less than 0, and N is equal to or less than 100;
the obtaining the two unequal preset index values in the preset sliding window includes:
acquiring an average value and a standard deviation of sampling data corresponding to each EWMA value in the preset sliding window;
Obtaining the sum of the average value and a first quotient, and obtaining a smaller value in the two unequal preset index values, wherein the first quotient is the quotient of N% and the standard deviation;
and obtaining the sum of the average value and a second quotient, and obtaining a larger value in the two unequal preset index values, wherein the second quotient is the quotient of M% and the standard deviation.
The two unequal preset index values in the preset sliding window can be used for setting a first closed zone, the first closed zone is more accurate than an upper limit zone and a lower limit zone which are manually set, the accuracy of a judging result is improved, and the situation that the generalization capability of a glue proportion detection model is reduced due to the fact that a proportion data safety zone is manually set in the related art is improved.
In some embodiments of the application, the method further comprises:
And under the condition that the proportion of the mixed glue is judged to be abnormal, sending out a mixed glue proportion abnormal reminding signal. Therefore, relevant staff can be reminded to take corresponding treatment measures in time, and adverse effects caused by abnormal proportion of mixed glue are reduced.
In a second aspect of the embodiment of the present application, a data anomaly detection device in a cell glue spreading procedure is provided, including:
the sampling module is used for sampling the proportion data of various glues in the mixed glue adopted in the cell gluing process to obtain sampling data;
The first acquisition module is used for acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time;
The second acquisition module is used for acquiring two unequal preset index values in a preset sliding window aiming at the first numerical value;
and the judging module is used for judging whether the proportion of the mixed glue is abnormal according to the two unequal preset index values.
The data abnormality detection device in the cell gluing procedure provided in the second aspect of the embodiment of the present application can achieve the same technical effects as the first aspect of the embodiment of the present application.
In a third aspect of the embodiments of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the computer program to implement the method for detecting data anomalies in a die-coating procedure according to any one of the embodiments of the present application.
The third aspect of the embodiment of the present application can achieve the same technical effects as the first aspect of the embodiment of the present application.
In a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, on which a computer program is stored, where the computer program is executed by a processor to implement a method for detecting a data anomaly in a cell glue spreading procedure according to any embodiment of the present application.
The fourth aspect of the embodiments of the present application can achieve the same technical effects as the first aspect of the embodiments of the present application.
The foregoing description is only an overview of the technical solutions of the embodiments of the present application, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present application can be more clearly understood, and the following specific embodiments of the present application will be more specifically described below.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the embodiments. The drawings are only for the purpose of illustrating embodiments of the application and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the accompanying drawings.
Fig. 1 is a flow diagram of a method for detecting data anomalies in a die attach process in accordance with one or more embodiments.
FIG. 2 is a flow diagram of step S10 in accordance with one or more embodiments.
FIG. 3 is a flow diagram of obtaining two unequal preset index values within a preset sliding window in accordance with one or more embodiments.
Fig. 4 is a schematic diagram of the results of offline analysis of glue ratio detection data of a cell glue application process according to one or more embodiments.
Fig. 5 is a graph of glue ratio detection data for mixed glue on an actual production line in accordance with one or more embodiments.
Fig. 6 is a block diagram of a data anomaly detection device in a cell glue process according to one or more embodiments.
FIG. 7 is a block diagram of an electronic device in accordance with one or more embodiments.
FIG. 8 is a schematic diagram of a computer-readable storage medium in accordance with one or more embodiments.
Detailed Description
Embodiments of the technical scheme of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and thus are merely examples, and are not intended to limit the scope of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs, the terms used herein are for the purpose of describing particular embodiments only and are not intended to be limiting of the application, and the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the above description of the drawings are intended to cover non-exclusive inclusions.
In the description of embodiments of the present application, the technical terms "first," "second," and the like are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present application, the meaning of "plurality" is two or more (including two) unless otherwise specifically defined.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The cell gluing process is an important step in battery production, is used for improving the tightness and structural strength of the battery and preventing leakage, and can also play roles of fixing, insulating and radiating the cell. When the cell gluing operation is performed, a proper coating mode such as uniform coating, strip coating and the like is selected according to the cell design, the glue coating amount is controlled, after the coating is completed, the curing treatment is performed according to the property of glue, and the curing can be performed in a mode of natural drying or heating curing and the like, so that the requirements of curing conditions are met, and a good glue bonding effect is achieved. Different cell materials or structures are suitable for glue with different characteristics, and the condition required by single glue curing is often not suitable for multiple application scenes or multiple cell materials or structures at the same time, so that mixed glue formed by mixing multiple glue is adopted in the cell gluing process in the related technology to optimize the bonding effect.
In practical application, when the proportion of various glues of the mixed glue is in a specific range, the mixed glue can reach better bonding strength, and the bonding strength can be influenced when the proportion of the mixed glue is abnormal. The related art lacks the monitoring to the proportion of various glues in the mixed glue in electric core rubber coating process, can't in time discover the unusual situation of glue proportion, and the mixed glue adhesion strength that the glue proportion is unusual leads to takes place more.
In view of the problems existing in the related art, the embodiment of the application provides a data anomaly detection method in a cell gluing process, which is used for sampling the proportion data of various glues in mixed glues adopted in the cell gluing process to obtain sampling data, under the condition that the number of the sampling data reaches a first numerical value, acquiring a preset index corresponding to each sampling data in the first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time, then acquiring two unequal preset index values in a preset sliding window according to the first numerical value, judging whether the proportion of the mixed glues is abnormal according to the two unequal preset index values, so that the proportion data of various glues in the mixed glues can be detected, the abnormal proportion condition of the glues can be found in time in the cell gluing process, and the condition that the bonding strength of the mixed glues is poor due to the abnormal proportion of the glues is reduced.
The data abnormality detection method in the cell gluing process provided by the embodiment of the application is suitable for application scenes including the cell gluing process, such as application scenes of battery manufacturing and the like.
The following describes a data anomaly detection method in a cell gluing process according to an embodiment of the present application with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present application provides a method for detecting data anomalies in a die-coating process, which may include steps S10 to S40:
S10, sampling proportion data of various glues in the mixed glue adopted in the cell gluing process to obtain sampling data.
The sampling data are glue proportion data detected by a glue proportion detecting instrument. Devices for detecting the proportions of the various glues in the mixed glue, including but not limited to, spectrum analyzers, gas chromatographs, liquid chromatographs (HPLC), mass Spectrometers (MS), and the like. The spectrum analyzer may for example employ a fourier transform infrared spectrometer (FTIR) to determine the proportions of the different glues by analysing the chemical composition of the mixed glue. Gas Chromatography (GC) can be used to determine the ratio of different glues by separating and quantifying the components. Liquid Chromatography (HPLC) can separate and quantify various glues of the mixed glue. A Mass Spectrometer (MS) may be used in conjunction with a chromatograph to provide a more accurate analysis of the components to determine the proportions of the various glues in the mixed glue.
Referring to fig. 2, in some embodiments, step S10 may include sampling the proportion data of various glues in the mixed glue to obtain an original sampling value, detecting whether the original sampling value is an abnormal value, S102, removing the original sampling value if the original sampling value is the abnormal value, filling the removed original sampling value, and taking the filled value as sampling data, and S104, taking the original sampling value as sampling data if the original sampling value is not the abnormal value. That is, the glue ratio of the sampling data to the abnormal value is the original sampling value. Outliers include, but are not limited to, extreme values, which are values that are very different from other sampled values. Outlier passes are due to instability or fluctuations in the sampling device. The original sample values that are removed can be padded using a KNN algorithm. The KNN algorithm (K-Nearest Neighbor) is also known as the K Nearest Neighbor method or Neighbor algorithm.
Therefore, abnormal values can be removed, interference caused by the abnormal values is reduced, and the accuracy of abnormal judgment results of various glue proportions in the mixed glue is further improved.
Illustratively, step S10 may further include storing the sampled data in a pre-established data queue having a first data value in accordance with the sampling time sequence. Thus, the management and the calling of the sampling data are facilitated, and the working efficiency is improved.
For example, sampling data are sequentially grabbed from sampling values accumulated at the current moment according to sampling time and stored in a pre-established data queue.
S20, under the condition that the number of the sampling data reaches a first value, acquiring a preset index corresponding to each sampling data in the first value sampling data.
The preset index is used for representing the trend of the sampled data along with the change of time. The preset indicators include, but are not limited to, an exponentially weighted moving average EWMA, a weighted moving average WMA, a double exponentially moving average DEMA, and the like. The first value is a predetermined positive integer.
For example, in the event that the number of sample data held in a pre-established data queue reaches a first value n, an exponentially weighted moving average of the data queue, EWMA i, is calculated, where i=1, 2. The calculation formula of the exponentially weighted moving average EWMA is
Wherein X (t) represents sampling data at the time t, and alpha is a preset weight.
The sampled data is processed by an exponentially weighted moving average EWMA algorithm to smooth the sampled data to reveal the trend of the sampled data over time and to reduce noise. The EWMA algorithm is beneficial to better capturing the recent change trend of the sampled data by applying decreasing weight to the sampled data so that the latest sampled data has a greater influence on the average value.
S30, aiming at a first numerical value, acquiring two unequal preset index values in a preset sliding window.
In some embodiments, the two unequal preset index values are respectively a preset index value of the nth percentile and a preset index value of the mth percentile, wherein both N and M are preset values, 0< N is less than or equal to 100,0< M is less than or equal to 100, and N < M. Referring to fig. 3, obtaining two unequal preset index values in a preset sliding window may include:
S301, acquiring an average value and a standard deviation of sampling data corresponding to each EWMA value in a preset sliding window;
S302, obtaining the sum of the average value and a first quotient, namely the quotient of N% and the standard deviation, to obtain a smaller value of the two unequal preset index values;
S303, obtaining the sum of the average value and a second quotient, namely the quotient of M% and the standard deviation, to obtain a larger value in the two unequal preset index values.
The two unequal preset index values in the preset sliding window can be used for setting a first closed zone, the first closed zone is used as a comparison zone for judging whether the proportion is abnormal or not, the first closed zone is more accurate than an upper limit zone and a lower limit zone which are manually set, the accuracy of a judging result is improved, and the situation that the generalization capability of a glue proportion detection model is reduced due to the fact that the proportion data safety zone is manually set in the related art is improved.
The values of N and M can be set according to the actual application requirements. For example, N can be set to 5, M to 95, forTaking 95% of the quantilesAnd 5% quantile,Wherein,,Represents the average number of times T,Represents the standard deviation at time T, D j represents the j-th sample data, and Q represents the original sample data.
S40, judging whether the proportion of the mixed glue is abnormal according to the two unequal preset index values.
In some embodiments, the preset index comprises an exponentially weighted moving average EWMA. The step of judging whether the proportion of the mixed glue is abnormal according to the two unequal preset index values can comprise judging whether the proportion of the mixed glue is abnormal according to the sampling data with the current sampling sequence number being a second numerical value and the two unequal preset index values, wherein the sampling sequence number is a sequence number for sequencing all the current sampling data according to the sampling time, and the second numerical value is the sum of the first numerical value and 1. For example, the first value is n, and the second value is n+1. The exponential weighted moving average EWMA is used as a preset index, so that the trend of the sampled data along with the time change can be revealed, and the noise can be reduced.
Exemplary, determining whether the proportion of the mixed glue is abnormal according to the current sampling data with the second numerical value and the two unequal preset index values includes:
Judging that the proportion of the mixed glue is normal when the current sampling data with the second numerical value belongs to a first closed interval, wherein the left end point of the first closed interval is smaller than the smaller value of the two unequal preset index values, and the right end point of the first closed interval is larger than the larger value of the two unequal preset index values;
And under the condition that the current sampling data with the sampling serial number of the second numerical value does not belong to the first closed interval, judging that the proportion of the mixed glue is abnormal.
The dynamic threshold is set based on the percentile of the data in the preset sliding window, so that the accuracy of a judgment result is improved, and false alarm and missing report of abnormal conditions caused by data fluctuation are reduced. Whether the proportion of the mixed glue is abnormal or not is judged by whether the current sampling data with the sampling sequence number of the second numerical value belongs to the first closed interval or not, and the accuracy rate of the judgment result is higher.
The left end point of the first closed interval is the product of the smaller value of the two unequal preset index values and the third value, the right end point of the first closed interval is the product of the larger value of the two unequal preset index values and the fourth value, the third value is smaller than 1, the fourth value is larger than 1, and the sum of the third value and the fourth value is 2.
For example, a preset assigned weight m=0.03, and the sampling data of the next time stamp is set asIf (if)Or (b)And judging that the proportion of the mixed glue is abnormal.
In some embodiments, the method may further include step S50, under the condition that the proportion of the mixed glue is normal, replacing the sampling data with the earliest sampling time in all the current sampling data with the second value of the current sampling sequence number, deleting the first EWMA, and returning to obtain the preset index corresponding to each sampling data in the first value of the sampling data, where the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.
Specifically, deleting the first data in the data queue, adding the sampled data with the second numerical value to the data queue to obtain an updated data queue, wherein the number of the sampled data in the updated data queue is still the first numerical value.
In this way, the sampling data with the current sampling sequence number of the second numerical value is used for replacing the sampling data with the earliest sampling time in all the current sampling data, the update of the original first numerical value sampling data is realized, the preset index corresponding to each sampling data in the first numerical value sampling data is returned and obtained after the first EWMA is deleted, the update of the first numerical value index weighted moving average EWMA is realized, the subsequent steps are continuously executed, the update of two unequal preset index values in a preset sliding window is realized, and finally whether the proportion of the mixed glue is abnormal is judged according to the updated two unequal preset index values, so that the dynamic adjustment of a comparison interval is realized. Through repeated execution, the abnormal online detection of the proportion data of the mixed glue in the cell gluing process is realized. Compared with the mode of clamping and controlling the upper limit and the lower limit of the fixed threshold in the related art, the method of the embodiment realizes the dynamic adjustment of the comparison interval, can consider the influence of the discrete degree of the sampled data, is easy to capture the abnormal fluctuation condition of the data, and can accurately and timely discover the abnormal proportion condition.
In some embodiments, the method may further include step S60 of sending a mixed glue proportion abnormality alert signal if it is determined that the proportion of the mixed glue is abnormal.
The mixed glue proportion abnormality reminding signal comprises but is not limited to an audible and visual alarm signal, a short message and the like, and can remind relevant staff to take treatment measures in time so as to realize timely and accurate early warning of the mixed glue proportion abnormality.
Fig. 4 shows a schematic diagram of a result of offline analysis of 16825 pieces of glue proportion detection data in total in a cell gluing process in a specific example, wherein the data is derived from MES (Manufacturing Execution System, a manufacturing execution system, the upper and lower lines of early warning in actual detection data are respectively 0.1, -0.1, normal values are not only required to be within the upper and lower limit ranges, and data under the optimal condition need to keep certain stability, the data exceeding the upper and lower limit is certain gluing abnormal data, and the data representing discrete data is also possible to be gluing abnormal data (case data exceeds a mean value by plus or minus 9, standard deviation is discrete abnormal data), and the data exceeding the upper limit of early warning is 2 pieces of detection data.
As shown in fig. 5, a glue proportion detection data diagram of mixed glue on an actual production line in a specific example is shown, a total of 1712 pieces of detection data show that 7 pieces of prediction overrun data exist before the detection of the abnormality detection data, and the abnormality data are identified in advance (38 hours in advance, and the horizontal axis represents time in the diagram), so that the purpose of early warning can be achieved, and the glue proportion detection monitoring level of cell glue is improved.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
A data anomaly detection method in a cell gluing process specifically comprises the steps of sampling proportion data of various glues in mixed glue to obtain an original sampling value in a sampling stage, detecting whether the original sampling value is an anomaly value, eliminating the original sampling value and filling the eliminated original sampling value under the condition that the original sampling value is the anomaly value, taking the filled value as sampling data, taking the original sampling value as the sampling data under the condition that the original sampling value is not the anomaly value, and storing the sampling data into a pre-established data queue according to sampling time sequence, wherein the capacity of the data queue is the first numerical value data.
Acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time;
For a first numerical value of preset indexes, firstly obtaining the average value and standard deviation of sampling data corresponding to each EWMA value in a preset sliding window, obtaining the sum of the average value and a first quotient to obtain a preset index value of a 5 th percentile, wherein the first quotient is the quotient of 5% and the standard deviation, then obtaining the sum of the average value and a second quotient to obtain a preset index value of a 95 th percentile, and the second quotient is the quotient of 95% and the standard deviation.
And under the condition that the current sampling data with the sampling sequence number of the second numerical value belongs to the first closed interval, judging that the proportion of the mixed glue is normal, wherein the left end point of the first closed interval is smaller than the preset index value of the 5 th percentile, and the right end point of the first closed interval is larger than the preset index value of the 95 th percentile.
And under the condition that the current sampling data with the second numerical value does not belong to the first closed interval, judging that the proportion of the mixed glue is abnormal, wherein the sampling serial number is a serial number for sequencing all the current sampling data according to the sampling time, the second numerical value is the sum of the first numerical value and 1, and the preset index is an exponential weighted moving average EWMA.
The left end point of the first closed interval is the product of the preset index value of the 5 th percentile and a third value, the right end point of the first closed interval is the product of the preset index value of the 95 th percentile and a fourth value, the third value is smaller than 1, the fourth value is larger than 1, and the sum of the third value and the fourth value is 2.
Under the condition that the proportion of the mixed glue is normal, replacing the sampling data with the earliest sampling time in all the current sampling data by using the sampling data with the second numerical value, deleting the first EWMA, and returning to obtain a preset index corresponding to each sampling data in the first numerical value, wherein the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.
And under the condition that the proportion of the mixed glue is judged to be abnormal, sending out a mixed glue proportion abnormal reminding signal.
The data anomaly detection method in the cell gluing process can detect the proportion data of various glues in the mixed glue, so that the situation of poor bonding strength of the mixed glue caused by the anomaly of the proportion of the glues can be found in time in the cell gluing process, the problems of abnormal false alarm and missing report caused by poor fitting precision of regression equations due to data fluctuation can be reduced, for example, the situation that the model generalization capability is reduced due to artificial setting of a safety interval in the related technology can be improved, the dynamic adjustment of a comparison interval is realized, the overstock situation is reduced, the recent change trend of sampling data can be captured by acquiring EWMA, and the dynamic comparison interval of the sampling data is set based on the percentile of the data in a sliding window, so that the accuracy of anomaly detection is improved, and the false alarm and missing report of the abnormal data caused by the data fluctuation are reduced.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
Referring to fig. 6, another embodiment of the present application provides a data anomaly detection device in a cell glue spreading process, including:
the sampling module is used for sampling the proportion data of various glues in the mixed glue adopted in the cell gluing process to obtain sampling data;
The first acquisition module is used for acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value;
the second acquisition module is used for acquiring two unequal preset index values in a preset sliding window aiming at the first numerical value preset index;
the judging module is used for judging whether the proportion of the mixed glue is abnormal or not according to the two unequal preset index values.
In some embodiments, the preset index includes an exponentially weighted moving average EWMA, and the judging module is further specifically configured to judge whether the proportion of the mixed glue is abnormal according to the sampled data with the current sampling sequence number being the second value and the two unequal preset index values, where the sampling sequence number is a sequence number for sequentially sequencing all the current sampled data according to the sampling time, and the second value is a sum of the first value and 1.
In some embodiments, the determining module is further specifically configured to:
Judging that the proportion of the mixed glue is normal when the current sampling data with the second numerical value belongs to a first closed interval, wherein the left end point of the first closed interval is smaller than the smaller value of the two unequal preset index values, and the right end point of the first closed interval is larger than the larger value of the two unequal preset index values;
And under the condition that the current sampling data with the sampling serial number of the second numerical value does not belong to the first closed interval, judging that the proportion of the mixed glue is abnormal.
In some embodiments, the left end point of the first closed interval is the product of the EWMA of the smaller value and a third value, the right end point of the first closed interval is the product of the EWMA of the larger value and a fourth value, the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2.
In some embodiments, the sampling module is further specifically configured to:
sampling the proportion data of various glues in the mixed glue to obtain an original sampling value;
Detecting whether an original sampling value is an abnormal value or not;
Under the condition that the original sampling value is an abnormal value, removing the original sampling value, filling the removed original sampling value, and taking the filled value as sampling data;
in the case where the original sample value is not an outlier, the original sample value is taken as the sample data.
In some embodiments, the sampling module may be further configured to store the sampled data in a pre-established data queue according to a sampling time sequence, where a capacity of the data queue is the first numerical value data.
In some embodiments, the device may further include a deletion module, where the deletion module is configured to replace, when the proportion of the mixed glue is normal, the sampling data with the earliest sampling time in all the current sampling data with the second sampling sequence number, delete the first EWMA, and return to obtain a preset index corresponding to each sampling data in the first sampling data, where the first EWMA is an EWMA corresponding to the sampling data with the earliest sampling time.
In some embodiments, the two unequal preset index values are respectively a preset index value of the nth percentile and a preset index value of the mth percentile, N and M are preset values, N is equal to or less than 100, M is equal to or less than 100, and N is equal to or less than 100, and the second obtaining module is further specifically configured to:
acquiring an average value and a standard deviation of sampling data corresponding to each EWMA value in a preset sliding window;
obtaining the sum of the average value and a first quotient, namely the quotient of N% and the standard deviation, to obtain a smaller value of the two unequal preset index values;
And obtaining the sum of the average value and a second quotient, namely the quotient of M% and the standard deviation, to obtain a larger value in the two unequal preset index values.
In some embodiments, the device may further include a reminding module, configured to send a mixed glue proportion abnormality reminding signal when it is determined that the proportion of the mixed glue is abnormal.
The data abnormality detection device in the cell gluing process provided by the embodiment of the application can detect the proportion data of various glues in the mixed glue, so that abnormal glue proportion conditions can be found in time in the cell gluing process, and the condition of poor adhesive strength of the mixed glue caused by abnormal glue proportion is reduced.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
Another embodiment of the present application provides an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement a method according to any of the above embodiments.
Referring to fig. 7, the electronic device 10 may include a processor 100, a memory 101, a bus 102 and a communication interface 103, where the processor 100, the communication interface 103 and the memory 101 are connected through the bus 102, and the memory 101 stores a computer program executable on the processor 100, and when the processor 100 executes the computer program, the method provided by any of the foregoing embodiments of the present application is executed.
The memory 101 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the device network element and the at least one other network element is achieved through at least one communication interface 103 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.
Bus 102 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. The memory 101 is configured to store a program, and the processor 100 executes the program after receiving an execution instruction, and the method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 100 or implemented by the processor 100.
The processor 100 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 100 or by instructions in the form of software. The processor 100 may be a general-purpose processor, and may include a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, and discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and, in combination with its hardware, performs the steps of the method described above.
The electronic device provided by the embodiment of the application and the method provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the electronic device and the method provided by the embodiment of the application due to the same inventive concept.
Another embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the method of any of the above embodiments. Referring to fig. 8, a computer readable storage medium is shown as an optical disc 20 having a computer program (i.e., a program product) stored thereon, which, when executed by a processor, performs the method provided by any of the embodiments described above.
It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.
The computer-readable storage medium provided by the above-described embodiments of the present application has the same advantageous effects as the method adopted, operated or implemented by the application program stored therein, for the same inventive concept as the method provided by the embodiments of the present application.
It should be noted that:
The term "module" is not intended to be limited to a particular physical form. Depending on the particular application, modules may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same components. There may or may not be clear boundaries between different modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with the examples herein. The required structure for the construction of such devices is apparent from the description above. In addition, the present application is not directed to any particular programming language. It will be appreciated that the teachings of the present application described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present application.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing examples merely illustrate embodiments of the application and are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (11)
1. The data anomaly detection method in the cell gluing process is characterized by comprising the following steps of:
sampling proportion data of various glues in mixed glues adopted in the cell gluing process to obtain sampling data;
Acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time;
Acquiring two unequal preset index values in a preset sliding window aiming at the first numerical value preset indexes;
Judging whether the proportion of the mixed glue is abnormal or not according to the two unequal preset index values;
The two unequal preset index values are respectively the preset index value of the Nth percentile and the preset index value of the Mth percentile, wherein N and M are preset values which are equal to or less than 100 and 0< N and equal to or less than 100, and N < M;
the obtaining the two unequal preset index values in the preset sliding window includes:
acquiring an average value and a standard deviation of sampling data corresponding to each EWMA value in the preset sliding window;
Obtaining the sum of the average value and a first quotient, and obtaining a smaller value in the two unequal preset index values, wherein the first quotient is the quotient of N% and the standard deviation;
and obtaining the sum of the average value and a second quotient, and obtaining a larger value in the two unequal preset index values, wherein the second quotient is the quotient of M% and the standard deviation.
2. The method of claim 1, wherein the predetermined index comprises an exponentially weighted moving average EWMA, and wherein the determining whether the ratio of the mixed glue is abnormal based on the two unequal predetermined index values comprises:
Judging whether the proportion of the mixed glue is abnormal or not according to the sampling data with the current sampling sequence number of a second numerical value and the two unequal preset index values, wherein the sampling sequence number is a sequence number for sequencing all the current sampling data according to sampling time, and the second numerical value is the sum of the first numerical value and 1.
3. The method according to claim 2, wherein the determining whether the proportion of the mixed glue is abnormal according to the sampling data with the current sampling number being the second value and the two unequal preset index values includes:
judging that the proportion of the mixed glue is normal when the current sampling data with the second sampling sequence number belongs to a first closed interval, wherein the left end point of the first closed interval is smaller than the smaller value of the two unequal preset index values, and the right end point of the first closed interval is larger than the larger value of the two unequal preset index values;
And under the condition that the current sampling data with the sampling serial number of the second numerical value does not belong to the first closed interval, judging that the proportion of the mixed glue is abnormal.
4. The method of claim 3, wherein the left end point of the first closed interval is the product of the EWMA of the smaller value and a third value, the right end point of the first closed interval is the product of the EWMA of the larger value and a fourth value, the third value is less than 1, the fourth value is greater than 1, and the sum of the third value and the fourth value is 2.
5. The method according to any one of claims 1 to 4, wherein the step of sampling the ratio data of each glue in the mixed glue used in the cell glue application process to obtain sampled data includes:
sampling the proportion data of various glues in the mixed glue to obtain an original sampling value;
Detecting whether an original sampling value is an abnormal value or not;
Removing the original sampling value under the condition that the original sampling value is an abnormal value, filling the removed original sampling value, and taking the filled value as sampling data;
and taking the original sampling value as the sampling data in the case that the original sampling value is not an abnormal value.
6. The method of claim 5, wherein the sampling the ratio data of the various glues in the mixed glue used in the cell glue application process to obtain the sampled data, further comprises:
And storing the sampled data into a pre-established data queue according to the sampling time sequence, wherein the capacity of the data queue is the first numerical value data.
7. The method according to any one of claims 2 to 4, further comprising:
And under the condition that the proportion of the mixed glue is normal, replacing the sampling data with the earliest sampling time in all the current sampling data by using the sampling data with the second numerical value, deleting the first EWMA, and returning to the preset index corresponding to each sampling data in the acquired first numerical value sampling data, wherein the first EWMA is the EWMA corresponding to the sampling data with the earliest sampling time.
8. The method according to any one of claims 1 to 4, further comprising:
And under the condition that the proportion of the mixed glue is judged to be abnormal, sending out a mixed glue proportion abnormal reminding signal.
9. The utility model provides a data anomaly detection device in electric core rubber coating process which characterized in that includes:
the sampling module is used for sampling the proportion data of various glues in the mixed glue adopted in the cell gluing process to obtain sampling data;
The device comprises a first acquisition module, a first sampling module and a second acquisition module, wherein the first acquisition module is used for acquiring a preset index corresponding to each sampling data in the first numerical value sampling data under the condition that the number of the sampling data reaches a first numerical value, wherein the preset index is used for representing the trend of the sampling data changing along with time;
The second acquisition module is used for acquiring two unequal preset index values in a preset sliding window aiming at the first numerical value;
The judging module is used for judging whether the proportion of the mixed glue is abnormal or not according to the two unequal preset index values;
the two unequal preset index values are respectively a preset index value of the Nth percentile and a preset index value of the Mth percentile, N and M are preset values which are equal to or less than 100,0< N < 100, and N < M, and the second acquisition module is further used for:
acquiring an average value and a standard deviation of sampling data corresponding to each EWMA value in the preset sliding window;
Obtaining the sum of the average value and a first quotient, and obtaining a smaller value in the two unequal preset index values, wherein the first quotient is the quotient of N% and the standard deviation;
and obtaining the sum of the average value and a second quotient, and obtaining a larger value in the two unequal preset index values, wherein the second quotient is the quotient of M% and the standard deviation.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the method of detecting data anomalies in a die-coating process as claimed in any one of claims 1 to 8.
11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method of detecting data anomalies in a cell glue process as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411799606.6A CN119272140B (en) | 2024-12-09 | 2024-12-09 | Method, device, equipment and medium for detecting data abnormality in cell gluing process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411799606.6A CN119272140B (en) | 2024-12-09 | 2024-12-09 | Method, device, equipment and medium for detecting data abnormality in cell gluing process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119272140A CN119272140A (en) | 2025-01-07 |
| CN119272140B true CN119272140B (en) | 2025-03-18 |
Family
ID=94105953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411799606.6A Active CN119272140B (en) | 2024-12-09 | 2024-12-09 | Method, device, equipment and medium for detecting data abnormality in cell gluing process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119272140B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570000A (en) * | 2021-09-08 | 2021-10-29 | 南开大学 | Ocean single-factor observation quality control method based on multi-model fusion |
| CN118455829A (en) * | 2024-07-15 | 2024-08-09 | 江苏时代新能源科技有限公司 | Battery welding quality detection method, device and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5279655B2 (en) * | 2009-08-07 | 2013-09-04 | 三菱電機株式会社 | Machine tool control system |
| CN113988593B (en) * | 2021-10-26 | 2024-07-26 | 浙江中烟工业有限责任公司 | Online diagnosis method for cigarette air leakage defect |
| CN115619748A (en) * | 2022-10-27 | 2023-01-17 | 中材科技（邯郸）风电叶片有限公司 | A monitoring method for abnormal glue color in the glue coating process of wind power blades |
| CN118708428A (en) * | 2024-05-28 | 2024-09-27 | 建信金融科技有限责任公司 | Data processing methods, devices, equipment, media and products |
-
2024
- 2024-12-09 CN CN202411799606.6A patent/CN119272140B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570000A (en) * | 2021-09-08 | 2021-10-29 | 南开大学 | Ocean single-factor observation quality control method based on multi-model fusion |
| CN118455829A (en) * | 2024-07-15 | 2024-08-09 | 江苏时代新能源科技有限公司 | Battery welding quality detection method, device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119272140A (en) | 2025-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116887569B (en) | Data center energy consumption prediction and energy saving adjustment method, system and storage medium | |
| US11215672B2 (en) | Battery detection method | |
| CN117556368B (en) | Water conservancy monitoring abnormal data processing method based on Internet of things | |
| CN117273195A (en) | Steam heating system demand load prediction method | |
| CN115936262A (en) | Big data based environmental disturbance yield prediction method, system, and medium | |
| CN111998918A (en) | Error correction method, error correction device and flow sensing system | |
| CN110276385A (en) | Similarity-Based Remaining Service Life Prediction Method of Mechanical Components | |
| CN119272140B (en) | Method, device, equipment and medium for detecting data abnormality in cell gluing process | |
| CN110888100A (en) | A single-phase smart energy meter online on-load detection system and method | |
| US11438994B2 (en) | Filament current control method and apparatus | |
| CN111257758B (en) | SOH estimation method for emergency lead-acid storage battery of power station | |
| CN113378350A (en) | Temperature change trend determination method and device and electronic equipment | |
| CN117406090B (en) | Lithium ion battery power consumption detection method and device | |
| CN118410422A (en) | Automatic sampling device and method for building construction | |
| CN117851953A (en) | Water use abnormality detection method, device, electronic apparatus, and storage medium | |
| CN117368835A (en) | Method and system for detecting out-of-tolerance based on current error value change of electric energy meter | |
| CN117216956A (en) | Device, method and equipment for correcting thermal-oxidative aging model of XLPE cable | |
| CN117131391A (en) | Enterprise energy consumption analysis and alarm method based on intelligent energy platform | |
| CN116910655A (en) | Intelligent ammeter fault prediction method based on device measurement data | |
| CN112747413B (en) | Air conditioning system load prediction method and device | |
| CN116092281B (en) | Calibration method, device, equipment and storage medium of bidirectional smoke detector | |
| CN113220656A (en) | Method and device for analyzing liquid crystal panel glass production data file | |
| CN116258424B (en) | Product analysis method, battery product analysis method, device, equipment and medium | |
| CN113254475B (en) | Historical data query and acquisition method for branch line monitoring terminal | |
| CN119355612B (en) | Self-calibration method of electric signal multichannel acquisition device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |